dot

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow queries a corporate database analytics service via dot, where assistant responses and fetched data summaries from third-party connected databases could contain outsider-authored input.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The installation script fetches and executes an external shell script and skill file from app.getdot.ai and GitHub via uncontrolled HTTP channels during user setup, constituting a high-risk unverifiable runtime external dependency.